Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases indicating distancing or opting out from situations or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    moving away from

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     requ
    -0.44
    Requ
    -0.39
     Gland
    -0.38
     Require
    -0.35
     engine
    -0.35
     plate
    -0.35
     Rady
    -0.35
     :::
    -0.34
     inspector
    -0.34
     Requ
    -0.34
    POSITIVE LOGITS
    ########.
    0.60
     away
    0.60
     Flucht
    0.58
     Autorizaciones
    0.58
     withdrawing
    0.57
     quitted
    0.57
     afast
    0.56
     withdrew
    0.56
    PreExecute
    0.56
    ंदीखरीदारी
    0.55
    Act Density 0.030%

    No Known Activations